Your browser doesn't support javascript.
loading
Artificial neural network prediction of post-thyroidectomy outcome.
Tsutsumi, Kotaro; Goshtasbi, Khodayar; Ahmed, Khwaja H; Khosravi, Pooya; Tawk, Karen; Haidar, Yarah M; Tjoa, Tjoson; Armstrong, William B; Abouzari, Mehdi.
Afiliación
  • Tsutsumi K; Department of Otolaryngology-Head and Neck Surgery, University of California, Irvine, California, USA.
  • Goshtasbi K; Department of Otolaryngology-Head and Neck Surgery, University of California, Irvine, California, USA.
  • Ahmed KH; Department of Otolaryngology-Head and Neck Surgery, University of California, Irvine, California, USA.
  • Khosravi P; Department of Otolaryngology-Head and Neck Surgery, University of California, Irvine, California, USA.
  • Tawk K; Department of Otolaryngology-Head and Neck Surgery, University of California, Irvine, California, USA.
  • Haidar YM; Department of Otolaryngology-Head and Neck Surgery, University of California, Irvine, California, USA.
  • Tjoa T; Department of Otolaryngology-Head and Neck Surgery, University of California, Irvine, California, USA.
  • Armstrong WB; Department of Otolaryngology-Head and Neck Surgery, University of California, Irvine, California, USA.
  • Abouzari M; Department of Otolaryngology-Head and Neck Surgery, University of California, Irvine, California, USA.
Clin Otolaryngol ; 48(4): 665-671, 2023 07.
Article en En | MEDLINE | ID: mdl-37096572
OBJECTIVES: The goal of this study was to develop a deep neural network (DNN) for predicting surgical/medical complications and unplanned reoperations following thyroidectomy. DESIGN, SETTING, AND PARTICIPANTS: The 2005-2017 American College of Surgeons National Surgical Quality Improvement Program (ACS-NSQIP) database was queried to extract patients who underwent thyroidectomy. A DNN consisting of 10 layers was developed with an 80:20 breakdown for training and testing. MAIN OUTCOME MEASURES: Three primary outcomes of interest, including occurrence of surgical complications, medical complications, and unplanned reoperation were predicted. RESULTS: Of the 21 550 patients who underwent thyroidectomy, medical complications, surgical complications and reoperation occurred in 1723 (8.0%), 943 (4.38%) and 2448 (11.36%) patients, respectively. The DNN performed with an area under the curve of receiver operating characteristics of .783 (medical complications), .709 (surgical complications) and .703 (reoperations). Accuracy, specificity and negative predictive values of the model for all outcome variables ranged 78.2%-97.2%, while sensitivity and positive predictive values ranged 11.6%-62.5%. Variables with high permutation importance included sex, inpatient versus outpatient and American Society of Anesthesiologists class. CONCLUSIONS: We predicted surgical/medical complications and unplanned reoperation following thyroidectomy via development of a well-performing ML algorithm. We have also developed a web-based application available on mobile devices to demonstrate the predictive capacity of our models in real time.
Asunto(s)
Palabras clave
Texto completo
Añadir a Mi BVS
Imprimir
XML
PubMed Links
Buscar en Google

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Asunto principal: Complicaciones Posoperatorias / Tiroidectomía Tipo de estudio: Etiology_studies / Observational_studies / Prognostic_studies / Risk_factors_studies Límite: Humans Idioma: En Revista: Clin Otolaryngol Asunto de la revista: OTORRINOLARINGOLOGIA Año: 2023 Tipo del documento: Article País de afiliación: Estados Unidos Pais de publicación: Reino Unido
Texto completo
Añadir a Mi BVS
Imprimir
XML
PubMed Links
Buscar en Google

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Asunto principal: Complicaciones Posoperatorias / Tiroidectomía Tipo de estudio: Etiology_studies / Observational_studies / Prognostic_studies / Risk_factors_studies Límite: Humans Idioma: En Revista: Clin Otolaryngol Asunto de la revista: OTORRINOLARINGOLOGIA Año: 2023 Tipo del documento: Article País de afiliación: Estados Unidos Pais de publicación: Reino Unido